Search Results for author:
Found 3 papers, 0 papers with code
Relieving the Plateau: Active Semi-Supervised Learning for a Better Landscape
Equipped with a few theoretical insights, we propose convergence rate control (CRC), an AL algorithm that selects unlabeled data to improve the problem conditioning upon inclusion to the labeled set, by formulating an acquisition step in terms of improving training dynamics.
Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control
We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL.
Almost Boltzmann Exploration
In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\log^{1+\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\alpha>0$ is a parameter of the algorithm.
